[PATCH] D46365: AMDGPU: Separate R600 and GCN TableGen files

[Jan Vesely via Phabricator via llvm-commits]

jvesely added a comment.

a quick update. running llc manually on the kernel .ll (dumped using CLOVER_DEBUG=llvm) produces correct assembly. Running it in clover generates incorrect code (dumped using CLOVER_DEBUG=native) and hangs GPU.



================
Comment at: lib/Target/AMDGPU/AMDGPUFeatures.td:52
+>;
+
----------------
gi complains about  blank line at the end of file here


================
Comment at: lib/Target/AMDGPU/R600ISelLowering.cpp:237
   }
+ 
+  // FIXME: This was moved from AMDGPUTargetLowering, I'm not sure if we
----------------
git complains about whitespace error in this location


Repository:
  rL LLVM

https://reviews.llvm.org/D46365